pentest-kali

pentest-kali is a command for Claude Code from Stickman230/claude-pentest. It costs 43 tokens per session (1,802 once invoked), scanned A, original, MIT.

A command that connects coding agents to a Metasploit-Kali Server, a remote service providing Kali Linux security tools. It checks the server, lists available tools, and tells agents to prefer the remote endpoints where configured.

In plain words
What is it for?
Use it to enter a server URL, verify its health endpoint, discover available Kali tools, and configure remote-tool preferences.
Why use it?
It confirms that the remote security-tool service is reachable before testing starts and explains connection failures.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the pentest plugin — 7 skills, 5 commands, 15 agents shipped together

Good fit Use it to enter a server URL, verify its health endpoint, discover available Kali tools, and configure remote-tool preferences.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/stickman230/claude-pentest/pentest-kali
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Stickman230/claude-pentest

Made for: Claude Code.

Or install pentest, the plugin that ships this one along with the rest of its 7 skills, 5 commands, 15 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pentest-kali

README.md
[![agentmods](https://agentmods.dev/badge/commands/stickman230/claude-pentest/pentest-kali/github.svg)](https://agentmods.dev/commands/stickman230/claude-pentest/pentest-kali)
Your own site
<a href="https://agentmods.dev/commands/stickman230/claude-pentest/pentest-kali"><img src="https://agentmods.dev/badge/commands/stickman230/claude-pentest/pentest-kali/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pentest-kali

Your own site · 80×15
<a href="https://agentmods.dev/commands/stickman230/claude-pentest/pentest-kali"><img src="https://agentmods.dev/badge/commands/stickman230/claude-pentest/pentest-kali.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01802
Opus 5 $0.00022 $0.00901
Sonnet 5 $0.00009 $0.00360
Haiku 4.5 $0.00004 $0.00180

Measured 10d ago against content hash 29f0917e3b6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pentest-kali scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -m 10 {mks_url}/health
plugins/pentest/commands/pentest-kali.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Output the following banner verbatim:

============================================================
[MKS — KALI TOOL CONNECTION]
============================================================

Step 1 — Collect MKS Server URL

Use AskUserQuestion to ask:

"MKS Server URL — What is the URL of your Metasploit-Kali Server? (e.g., http://192.168.1.10:5000 or http://kali:5000)"

Store the answer as mks_url. Strip any trailing slash from the value.

Step 2 — Verify Connectivity

Run Bash:

curl -s -m 10 {mks_url}/health

Store the full response body as health_response.

If the Bash command fails (non-zero exit code), or if health_response is empty, output this block verbatim and stop:

============================================================
CONNECTION FAILED
============================================================
Could not reach MKS server at {mks_url}.

Possible causes:
  - Server is not running (start with: python server.py)
  - URL or port is incorrect
  - Firewall is blocking the connection
  - SSH tunnel is not established

Run /pentest:pentest-kali again once the server is reachable.
============================================================

If health_response is non-empty, parse it as JSON. If the status field is not "healthy", output:

============================================================
SERVER UNHEALTHY
============================================================
MKS server responded but reported status: {status}
Message: {message}

The server is running but essential tools may be missing.
Check that nmap, gobuster, dirb, and nikto are installed on the Kali host.
============================================================

Then stop.

Step 3 — Parse Tool Availability

From the parsed health_response, extract the reported booleans:

  • nmap_ok = value of tools_status.nmap (true/false, default false if missing)
  • gobuster_ok = value of tools_status.gobuster
  • dirb_ok = value of tools_status.dirb
  • nikto_ok = value of tools_status.nikto

Read the full file on GitHub · 211 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 211 lines · 43 tokens per session scan A 29f0917e3b6e

Subscribe to this mod's changes

pentest-kali is a command published in the GitHub repository Stickman230/claude-pentest (100 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,802 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.